Find events by specific tags or categories
AI agents call get_events_by_tag to retrieve information from OSU MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only tool that searches and retrieves event information filtered by tags or categories. It queries existing data without creating, modifying, deleting, or executing any operations. The low severity reflects minimal risk even in case of misuse—an AI agent can at worst retrieve unwanted event information, which has no destructive or financial impact.
From the tool's definition Tool name 'get_events_by_tag' and description 'Find events by specific tags or categories' indicate a query/retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Find events by specific tags or categories. It is categorised as a Read tool in the OSU MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OSU MCP Server MCP server in PolicyLayer and add a rule for get_events_by_tag: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches OSU MCP Server. Nothing to install.
get_events_by_tag is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_events_by_tag rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_events_by_tag. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_events_by_tag is provided by the OSU MCP Server MCP server (sichengchen/ohio-state-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →